AI & ML
Safe Personal RSI: Evaluating and Repairing Personal-Agent Updates
arXiv cs.SE0 views
arXiv:2611.23651v1 Announce Type: new Abstract: Kicker is a personal health assistant. Changes to an assistant's reusable instructions can improve task handling while changing what it discloses, which requests it follows, and how it reports actions. We study Safe Personal RSI, an update-evaluation component developed for Kicker. We restrict recursive self-improvement (RSI) to prompt updates, with model weights and runtime code fixed. The procedure tests proposed and current instructions, repeats failing cases, temporarily undoes changes to guide repairs, and checks safety and task performance before adoption. If no version passes, the current instructions stay in use. Our executable benchmark contains 29 email, calendar, health, and marketplace cases, with separate probes for authorization reuse, memory, and tool-output injection. Across three models and two deliberately risky edits, the procedure rejects 20 of 21 update attempts. In repair confirmation, an admitted GPT-5.6 Luna repair reduces attack violations from 10.7% to 0% and increases safe task completion from 89.7% to 100%; a broad handwritten authority rule matches these outcomes. Under stronger attacks, a repair transferred from Qwen2.5-7B-Instruct to Qwen3-14B reduces violations from 69.0% to 17.9% and increases safe task completion from 19.5% to 64.4%. Separate runtime probes examine memory-entry deletion and identify missing local OAuth scope checks in the evaluated snapshot.
Source:https://arxiv.org/abs/2611.23651PreviousOption-GRPO: Hierarchical RL Against AI Slop in Code Generation for Unseen SDKsNextCratesBump: A Version-Bump Dataset for the Rust Ecosystem
Related posts
The draft is not the send
0dev.to Discuss

My First GitHub Issue & My First Forem (DEV.to) Issue 🚀
0dev.to Discuss
Multimodel AI for Business: How to Build a Reliable Video Content Workflow
0dev.to Productivity
Your Thanksgiving flight home is on the busiest travel day of the year
0dev.to Productivity
Audit Week: When Your AI Assistant Knows Your Website Better Than You
0dev.to Productivity

Telegram เตรียม Dictator: AI Agent บน Mac ที่รายงานว่ารันบน Hermes Agent
0dev.to Machine Learning